Applying Information Retrieval (IR) techniques on model retrieval is a task that is gaining more importance with the fast growing number of computational biological models stored in model data bases. A thorough annotation of computational models enhances the semantic description of the modeled system by far. Efforts for enhanced model annotation, such as the Minimum Information Requested in the Annotation of Biochemical Models (MIRIAM) approach, are already applied to some modeling formalisms, e. g. the Systems Biology Markup Language (SBML). One prerequisite for the intended reuse of existing models is the ability to find them, i. e. to efficiently retrieve them from a model repository. However, the current state-of-the-art is to provide the user with an unranked list of models for his query, for example sorted by model ID as currently done in BioModels Database. We believe that a ranked search result will help the user to find the models relevant to his work. That is why we propose to use sophisticated retrieval techniques to sort the search results regarding different aspects. These techniques consider different information source; an important one being the aforementioned MIRIAM annotations. The developed concept is based on a similarity function for biological computational models that provides users a ranked set of models for a given query. It incorporates ideas from the area of Multimedia Information Retrieval (MIR), namely the Metadata-based similarity measure, the Content-based similarity measure, and the Semantic-description-based similarity measure. The advantage of our approach is a very fine-granular determination of similarity of the defined features. In this software demonstration we show how our concept of ranked model retrieval has been implemented as part of BioModels Database. The user now is enabled to specify what criteria are relevant for his search; and he is provided with a ranked result set of relevant models. The retrieval and ranking process incorporates different sources; besides the model itself, also descriptions of encoded constituents, the related reference publication and other meta data is used and can be queried. Moreover, several state-of-the-art IR features are supported, like fuzzy, proximity or range search.