The NOMAD-UVIS instrument on board the ExoMars Trace Gas Orbiter has been investigating the Martian atmosphere with the occultation technique since April 2018. Here, we analyze almost two Mars Years of ozone vertical distributions acquired at the day-night terminator. The ozone retrievals proved more difficult than expected due to spurious detections of ozone caused by instrumental effects, high dust content, and very low values of ozone. This led us to compare the results from three different retrieval approaches: (a) an onion peeling method, (b) a full occultation Optimal Estimation Method, and (c) a direct onion peeling method. The three methods produce consistently similar results, especially where ozone densities are higher. The main challenge was to find reliable criteria to exclude spurious detections of O3, and we finally adopted two criteria for filtering: (a) a detection limit, and (b) the Δχ2 criterion. Both criteria exclude spurious O3 values especially near the perihelion (180° < Ls < 340°), where up to 98% of ozone detections are filtered out, in agreement with general circulation models, that expect very low values of ozone in this season. Our agrees well with published analysis of the NOMAD-UVIS data set, as we confirm the main features observed previously, that is, the high-altitude ozone peak around 40 km at high latitudes. The filtering approaches are in good agreement with those implemented for the SPICAM/MEx observations and underline the need to evaluate carefully the quality of ozone retrievals in occultations.