This paper explores the use of methods and mechanisms from case-based reasoning for spatial cognition. In particular, it discusses approaches for tasks where an agent has knowledge available in various formats, and needs to make a choice for the most suitable one. The idea is to view the agent's repository of previously solved spatial problems as a case base and to store information of the representation used to solve each problem along with the case. Similarity measures can then be implemented that allow for the comparison of a new spatial problem to previously solved problems. Knowledge of spatial representations used to solve a previous problem can then help an agent reasoning with spatial knowledge to choose a suitable representation, based on the problem structure. Through the technique of case-based reasoning, we explore a possible answer to the question of how a software agent may choose one of several available spatial representations to perform a processing task.