Multidimensional image retrieval (MIR) views an image as a multidimensional object, where each dimension is a channel for retrieval. MIR has the potential of putting at work together the many methods and techniques for image retrieval proposed in several different fields of computer science. We have developed a model of MIR, based on a fuzzy description logic, that identifies two main dimensions in an image (form and content) and views MIR as a special form of uncertain implication. In this paper, we present ARIANNA, a system that implements the model. ARIANNA allows to quickly develop a prototype of a MIR application, and use it to test the adequacy of the application to the user's functional requirements.