Annotations are useful to semantically enrich documents and other datasets with concepts of standardized vocabularies and ontologies. In the medical domain, many documents are not annotated at all and manual annotation is a difficult and time-consuming process. Therefore, automatic annotation methods become necessary to support human annotators with recommendations. We propose a reuse-based annotation approach that clusters items in medical documents according to verified ontology-based annotations. We identify a set of representative features for annotation clusters and propose a context-based selection strategy that considers the semantic relatedness and frequent co-occurrences of annotated concepts. We evaluate our methods and the annotation tool MetaMap based on reference mappings between medical forms and the Unified Medical Language System.