Organizations invest many resources and time for improving business process and cooperative work. Traditional process mapping requires a lot of effort to diagnostic performance issues and to understand the main causes of losses. Process mining emerges as a new discipline focused on analyzing process based on real event data aimed to automate discovery of process models; to check conformance and to extend models performance or resource analysis. This paper combines a discovery process mining and a process variant clustering algorithm, focused on obtaining knowledge for a top-down navigation concerning performance cause analysis. An applied industry case was conducted to verify the proposed techniques using a dataset extracted from an ERP. From the results obtained, it was possible to identify the main performance losses segregated by process variants.