The NoSQL systems make it possible to manage Databases (DB) verifying the 3Vs: Volume, Variety andVelocity. Most of these systems are characterized by the property schemaless which means absence of thedata schema when creating a DB. This property provides undeniable flexibility by allowing the schema toevolve while the DB is in use; however, it is a major obstacle for developers and decision makers. Indeed, theexpression of queries (SQL type) requires precise knowledge of this schema. In this article, we provide aprocess for automatically extracting the schema from a NoSQL document-oriented DB. To do this, we usethe MDA (Model Driven Architecture). From a NoSQL DB, we propose transformation rules to generate theschema. An experiment of the extraction process was carried out on a medical application.