Visual Evoked Potential (VEP) is used for the diagnostics of seizure disorders, such as epilepsy. In order to analyze the VEP, variations of the neural electric tensions on the area of visual cortex in the occiput are measured by Electroencephalography (EEG) and Magnetoencephalography (MEG). Traditionally identification of VEP depends on the visual inspection of components by an expert. Currently supervised machine learning techniques have been applied to replace or to complement the visual inspection performed by the expert. In this paper, we propose an unsupervised framework for the identification of VEP in MEG measurements. In order to identify the VEP, we separate the measurement into two groups: the measurement without VEP and the measurements with VEP. Next, we compare the components from both groups in order to identify the components with VEP in the measurements with VEP. We validate our results using measurements from the Jena University Hospital.