This paper presents a novel platform for image retrieval based on a two-level architecture inspired from human cognitive mechanisms. These two levels provide both generic similarity and semantic information related to special characteristics. Although the proposed architecture can be customised for any content-based image retrieval application, our work is focused on medical images and more specifically on brain MRI data. Our main motivation is that in medical applications, it is crucial to be able to combine in an efficient way, image similarity with specific, semantics related to pathology in order to provide the user with relevant cases and aid diagnosis. A description of the architecture and function of the proposed CBIR platform is presented, as well as specific details for the application to brain MRI retrieval.